HMS-Net: Hierarchical Multi-scale Sparsity-invariant Network for Sparse Depth Completion

TL;DR

HMS-Net is a novel hierarchical multi-scale network that effectively completes sparse depth maps from LIDAR data by using sparsity-invariant operations, achieving top performance on benchmark datasets without relying heavily on RGB data.

Contribution

The paper introduces three new sparsity-invariant operations and a multi-scale encoder-decoder architecture for improved sparse depth completion.

Findings

Achieves state-of-the-art results on KITTI and NYU datasets.

Ranks first among peer-reviewed methods without RGB guidance on KITTI.

Ranks second among RGB-guided methods on KITTI.

Abstract

Dense depth cues are important and have wide applications in various computer vision tasks. In autonomous driving, LIDAR sensors are adopted to acquire depth measurements around the vehicle to perceive the surrounding environments. However, depth maps obtained by LIDAR are generally sparse because of its hardware limitation. The task of depth completion attracts increasing attention, which aims at generating a dense depth map from an input sparse depth map. To effectively utilize multi-scale features, we propose three novel sparsity-invariant operations, based on which, a sparsity-invariant multi-scale encoder-decoder network (HMS-Net) for handling sparse inputs and sparse feature maps is also proposed. Additional RGB features could be incorporated to further improve the depth completion performance. Our extensive experiments and component analysis on two public benchmarks, KITTI depth completion benchmark and NYU-depth-v2 dataset, demonstrate the effectiveness of the proposed approach. As of Aug. 12th, 2018, on KITTI depth completion leaderboard, our proposed model without RGB guidance ranks first among all peer-reviewed methods without using RGB information, and our model with RGB guidance ranks second among all RGB-guided methods.